Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Laplace Meets Moreau: Smooth Approximation to Infimal Convolutions Using Laplace's Method
Ryan J. Tibshirani, Samy Wu Fung, Howard Heaton, Stanley Osher
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use more samples N in the Laplace approximation | Laplace HJ approximation · Hamilton-Jacobi equation, d=2, p in {2,5,10} | HJ residual | Improved |
| increase smoothing parameter delta when samples are few | Laplace HJ approximation · Hamilton-Jacobi equation, few samples | HJ residual | Improved |
| increase dimension from d=2 to larger d | Laplace HJ approximation · Hamilton-Jacobi equation, d in {2,5,10} | HJ residual | Hurt |
| use Laplace-proximal point instead of tuned gradient descent | Laplace-proximal point · Benchmark suite, d=10 (ellipsoidal, discus) | criterion value | Improved |
| use Laplace-proximal point instead of tuned gradient descent | Laplace-proximal point · Benchmark suite, d=10 (rosenbrock, sharp ridge) | criterion value | Improved |
| use Laplace-proximal point instead of gradient descent on the convex well-conditioned sphere | Laplace-proximal point · Sphere benchmark, d=10 | criterion value | Hurt |
| increase N and decrease delta in Laplace-proximal point | Laplace-proximal point · Weierstrass benchmark, d=10 | criterion value | No clear effect |
| use Laplace-proximal point instead of random gradient-free oracle (N=1000) | Laplace-proximal point · Benchmark suite, d=10, N=1000 | criterion value | Mixed |
| average over multiple Gaussian draws in RGF | RGF · Benchmark suite, d=10 | criterion value | Improved |
Closest papers by meaning
- FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning (NeurIPS 2024 · similarity 0.83)
- On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality (ICLR 2025 · similarity 0.83)
- Exploring Jacobian Inexactness in Second-Order Methods for Variational Inequalities: Lower Bounds, Optimal Algorithms and Quasi-Newton Approximations (NeurIPS 2024 · similarity 0.83)
- Learning Theory of Transformers: Local-to-Global Approximation via Softmax Partition of Unity (NeurIPS 2026 · similarity 0.83)
- Nonlinearly Preconditioned Gradient Methods under Generalized Smoothness (ICML 2025 · similarity 0.83)
- Functional Gradient Flows for Constrained Sampling (NeurIPS 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
